Systems and methods for vehicle spatial path sampling

Abstract

Systems and methods for vehicle spatial path sampling are provided. The method includes obtaining an initial travel path for an autonomous vehicle from a first location to a second location and vehicle configuration data indicative of one or more physical constraints of the autonomous vehicle. The method includes determining one or more secondary travel paths for the autonomous vehicle from the first location to the second location based on the initial travel path and the vehicle configuration data. The method includes generating a spatial envelope based on the one or more secondary travel paths that indicates a plurality of lateral offsets from the initial travel path. And, the method includes generating a plurality of trajectories for the autonomous vehicle to travel from the first location to the second location such that each of the plurality of trajectories include one or more lateral offsets identified by the spatial envelope.

What is claimed is: 
     
         1 . A computer-implemented method, the method comprising:
 (a) obtaining data indicative of an initial travel path;   (b) obtaining data indicative of one or more constraints associated with one or more vehicle curvature limitations of an autonomous vehicle, the one or more vehicle curvature limitations determined based on physical capabilities of the autonomous vehicle;   (c) generating a plurality of trajectories for the autonomous vehicle based at least in part on the initial travel path;   (d) filtering at least one trajectory from the plurality of trajectories to generate a filtered plurality of trajectories, wherein filtering the at least one trajectory comprises determining that the at least one trajectory of the plurality of trajectories violates at least one of the one or more vehicle curvature limitations of the autonomous vehicle;   (e) selecting a selected trajectory from the filtered plurality of trajectories;   (f) generating a motion plan for the autonomous vehicle based on the selected trajectory; and   (g) controlling a motion of the autonomous vehicle based at least in part on the motion plan.   
     
     
         2 . The computer-implemented method of  claim 1 , wherein the one or more vehicle curvature limitations comprise one or more of maximum twist steering angle, maximum steering angle velocity, or a maximum angular velocity. 
     
     
         3 . The computer-implemented method of  claim 1 , wherein the initial travel path for the autonomous vehicle comprises a plurality of spatial coordinates corresponding to one or more times. 
     
     
         4 . The computer-implemented method of  claim 3 , wherein the initial travel path for the autonomous vehicle is associated with a curvature based at least in part on the plurality of spatial coordinates. 
     
     
         5 . The computer-implemented method of  claim 1 , wherein determining that the at least one trajectory of the plurality of trajectories violates at least one of the one or more vehicle curvature limitations of the autonomous vehicle comprises determining that the autonomous vehicle passes outside a spatial envelope defined by the one or more vehicle curvature limitations. 
     
     
         6 . The computer-implemented method of  claim 5 , wherein the spatial envelope represents a space that is viable for the autonomous vehicle to travel according to a respective trajectory. 
     
     
         7 . The computer-implemented method of  claim 6 , wherein the spatial envelope is indicative of a plurality of spatial coordinates between at least one minimum travel path and at least one maximum travel path. 
     
     
         8 . The computer-implemented method of  claim 7 , wherein the at least one minimum travel path is indicative of a minimum curvature of the autonomous vehicle, wherein the minimum curvature is indicative of a minimum viable driving angle for the autonomous vehicle, and
 wherein the at least one maximum travel path is indicative of a maximum curvature for the autonomous vehicle, wherein the maximum curvature is indicative of a maximum viable driving angle for the autonomous vehicle.   
     
     
         9 . The computer-implemented method of  claim 1 , wherein (e) comprises:
 determining a cost of the selected trajectory based at least in part on a cost function; and   determining that the cost of the selected trajectory is lower than at least one other trajectory of the plurality of filtered trajectories.   
     
     
         10 . The computer-implemented method of  claim 9 , wherein the cost function is based on costs associated with: (i) an acceleration of the autonomous vehicle, (ii) a smoothness of the autonomous vehicle, (iii) a velocity of the autonomous vehicle, and (iv) avoidance of an object. 
     
     
         11 . The computer-implemented method of  claim 1 , wherein (g) comprises:
 determining one or more control inputs to implement the motion plan; and   providing the one or more control inputs to a vehicle control system to utilize in controlling the motion of the autonomous vehicle.   
     
     
         12 . The computer-implemented method of  claim 1 , wherein the autonomous vehicle is a truck. 
     
     
         13 . An autonomous vehicle computing system comprising:
 one or more processors; and   one or more tangible, non-transitory, computer readable media that store instructions that are executable by the one or more processors to cause the computing system to perform operations comprising:   (a) obtaining data indicative of an initial travel path;   (b) obtaining data indicative of one or more constraints associated with one or more vehicle curvature limitations of an autonomous vehicle, the one or more vehicle curvature limitations determined based on physical capabilities of the autonomous vehicle;   (c) generating a plurality of trajectories for the autonomous vehicle based at least in part on the initial travel path;   (d) filtering at least one trajectory from the plurality of trajectories to generate a filtered plurality of trajectories, wherein filtering the at least one trajectory comprises determining that the at least one trajectory of the plurality of trajectories violates at least one of the one or more vehicle curvature limitations of the autonomous vehicle;   (e) selecting a selected trajectory from the filtered plurality of trajectories;   (f) generating a motion plan for the autonomous vehicle based on the selected trajectory; and   (g) controlling a motion of the autonomous vehicle based at least in part on the motion plan.   
     
     
         14 . The autonomous vehicle computing system of  claim 13 , wherein determining that the at least one trajectory of the plurality of trajectories violates at least one of the one or more vehicle curvature limitations of the autonomous vehicle comprises determining that the autonomous vehicle passes outside a spatial envelope defined by the one or more vehicle curvature limitations. 
     
     
         15 . The autonomous vehicle computing system of  claim 14 , wherein the spatial envelope represents a space that is viable for the autonomous vehicle to travel according to a respective trajectory. 
     
     
         16 . The autonomous vehicle computing system of  claim 14 , wherein the spatial envelope comprises a valid curvature range defined by a minimum viable driving angle for the autonomous vehicle and a maximum viable driving angle for the autonomous vehicle. 
     
     
         17 . The autonomous vehicle computing system of  claim 14 , wherein (d) comprises filtering one or more of the plurality of trajectories that, at least partially, extend outside the spatial envelope. 
     
     
         18 . The autonomous vehicle computing system of  claim 13 , wherein (d) comprises filtering the plurality of trajectories based at least in part on a cost function that provides a respective cost for each of the plurality of trajectories. 
     
     
         19 . The autonomous vehicle computing system of  claim 13 , wherein (d) comprises generating a respective speed profile for each trajectory of the plurality of trajectories and filtering the plurality of trajectories based at least in part on the respective speed profiles. 
     
     
         20 . One or more tangible, non-transitory, computer readable media that store instructions that are executable by one or more processors to cause the one or more processors to perform operations comprising:
 (a) obtaining data indicative of an initial travel path;   (b) obtaining data indicative of one or more constraints associated with one or more vehicle curvature limitations of an autonomous vehicle, the one or more vehicle curvature limitations determined based on physical capabilities of the autonomous vehicle;   (c) generating a plurality of trajectories for the autonomous vehicle based at least in part on the initial travel path;   (d) filtering at least one trajectory from the plurality of trajectories to generate a filtered plurality of trajectories, wherein filtering the at least one trajectory comprises determining that the at least one trajectory of the plurality of trajectories violates at least one of the one or more vehicle curvature limitations of the autonomous vehicle;   (e) selecting a selected trajectory from the filtered plurality of trajectories;   (f) generating a motion plan for the autonomous vehicle based on the selected trajectory; and   (g) controlling a motion of the autonomous vehicle based at least in part on the motion plan.